The last decade has seen an increase in the application of machine learning (ML) methods to PET/MRI attenuation correction (AC). This systematic review provides a head-to-head comparison between state-of-the-art ML methods and clinical standards for AC to determine the clinical feasibility of ML approaches PET AC. We extracted numerical values for image quality, tissue classification, regional and global diagnostic performance. The pooled mean relative error for global performance was 0.87 ± 1.3%, the quality of evidence for all outcomes ranged from moderate to very low. Our findings suggest that ML-AC performance is within acceptable limits for clinical PET/MR neuroimaging.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords